I recently took my Tesla Model Y running Full Self-Driving (Supervised) v14.3.3 over 150 miles on the Pennsylvania Turnpike in an effort to truly put the system under a stress test. There were a lot of good moments, and some bad, but overall, Full Self-Driving impressed me.

Last Thursday, I decided it was time to visit the Flight 93 National Memorial near Shanksville, PA. I go a few times a year, and it was a beautiful day. Others have taken some pretty lengthy drives using FSD, but I haven’t had the opportunity to really do something lengthy in quite a few months on an older version. I decided it was the perfect opportunity to try some things out.

I recorded the entire ride there on a GoPro, edited to highlight the crucial moments, and shared them on our social media accounts. If you want to watch them, I’ll share them throughout the piece, but I did not get to do a real breakdown of what I felt about its performance.

Overall Thoughts

I realize it is probably better to do a summation of its performance toward the end of the piece, but I feel like it is also reasonable to lead with this because I was overly impressed with how well it handled everything. The only moments where I felt a little bit of reason to touch the wheel, at least while traveling on the Turnpike and Rt. 30, were due to other drivers and their behaviors.

I have taken many drives to the Memorial over the past several years, and although it’s not incredibly long, it is a tiring drive. It’s about five hours both ways, close to 300 miles, and I think most of the exhaustion comes from the toll of sitting in the car and then visiting something that is pretty heavy to take in.

This was the first time I’ve ever taken the ride and not felt like I needed to avoid my vehicle after I got home. In the past, I could not even think about driving after I finally arrived at my house, but this was simply different.

It was nice to have something else take the drive for me, while I still had the freedom to take over if I chose to. It made the entire trip more enjoyable.

Full Self-Driving Recognizes Lane-Ending Arrows on Road

After traveling in the fast lane for a little while, FSD noticed the arrows on the road indicating the lane was coming to an end ahead. The car was also in the process of making a pass on a slower vehicle in the middle lane, but aborted this maneuver and backed off to get behind the vehicle.

I was really impressed by this because I thought that the car would absolutely try to make the pass, only to get in front of the other car, and then slow back down to 75 MPH:

WATCH: Tesla Full Self-Driving v14.3.3 recognizes lane-ending arrows, aborts pass of slower traffic, and gets in line https://t.co/1dxvTOw5Cn pic.twitter.com/SOpuj9ZHyP

— TESLARATI (@Teslarati) June 2, 2026

Full Self-Driving Notices Veering Tractor Trailer, Adjusts Lane Positioning

My two rules of the road are never cruise in the fast lane and never drive next to a tractor-trailer. This clip is a perfect example as to why.

FSD v14.3.3 recognized this tractor-trailer attempting to change lanes while we were still next to it. The car shifted its lane positioning to the shoulder slightly to make room for the merging semi, executed the pass safely, and on we went.

I will admit this one made me a little nervous, but more so because of the 18-wheeler, and not because of the Tesla:

WATCH: Tesla Full Self-Driving v14.3.3 notices tractor-trailer veering into lane, shifts lane positioning to create space, completes pass safely https://t.co/1dxvTOw5Cn pic.twitter.com/E35UrP79CH

— TESLARATI (@Teslarati) June 2, 2026

Full Self-Driving Follows the Rules of Tunnel Travel

Many people who are not familiar with Full Self-Driving and its capabilities are pretty limited in what they know about the really simple things it does well. Part of supervising FSD is being aware of things it might make mistakes with, and anticipating maneuvers it might want to make at the wrong time.

Entering the Blue Mountain Tunnel on the Turnpike, I was ready for FSD to attempt to get back into the right lane after making a pass on a tractor-trailer, but I was pleasantly surprised. Several signs outside the tunnel advise drivers to stay in the lane they’ve chosen while driving through the tunnel; this eliminates the possibility of an accident caused by lane changes, which would impede traffic on a crucial logistics route.

I was happy to see that Tesla Full Self-Driving v14.3.3 did not make this mistake:

WATCH: Tesla Full Self-Driving follows rules of tunnel travel, recognizes double lines, and does not change lanes https://t.co/1dxvTOw5Cn pic.twitter.com/L6eEP5bCE9

— TESLARATI (@Teslarati) June 2, 2026

Advertisement

Full Self-Driving Navigates Toll Plazas with Ease

I was interested to see how FSD would handle toll plazas, including the speed at which it would travel through them, and whether it would stop on the Turnpike at these booths, which have since been transitioned to a “Toll by Plate” system, which mails you a bill.

It was flawless:

WATCH: Tesla Full Self-Driving v14.3.3 seamlessly handles toll plaza, smoothly merges back onto Turnpike https://t.co/1dxvTOw5Cn pic.twitter.com/XmwY7rkj9J

— TESLARATI (@Teslarati) June 2, 2026

Advertisement

Full Self-Driving Still Struggles with Parking from Time to Time

Since I took delivery in late August, I’ve never had a single instance of my Tesla struggling to park at a Supercharger. Other spots at the mall, market, or gym are another story.

This was the first time it did such a terrible job of backing into a spot. This required me to take over and manually park at another charger:

Tesla Full Self-Driving v14.3.3 had trouble backing into the Fort Littleton, PA Supercharger, even though it was the only vehicle there.

This required manual parking. https://t.co/1dxvTOw5Cn pic.twitter.com/7xgqH2Z0ye

Advertisement

— TESLARATI (@Teslarati) June 2, 2026

Full Self-Driving Gets Confused After Arriving at Its Destination

This was the first time I have ever experienced FSD getting confused and just circling the lot. The navigation continued to reroute to try to resolve the issue, but after four laps, I decided it was time to overtake the car’s controls and park manually:

Experienced the same thing a few days ago

I think one of the big features a lot of people would appreciate is parking preferences or spot selection https://t.co/RCVwUOMxoY pic.twitter.com/U9f1wW2np9

Advertisement

— TESLARATI (@Teslarati) May 31, 2026

This was a baffling behavior that I truly couldn’t explain. Other owners communicated that they have also experienced this issue.

Final Thoughts

I am so incredibly impressed by FSD that it has really made traveling stress-free. The two issues related to parking were not ideal, but to be fair, I usually take over when arriving at parking lots. However, this shortcoming is something Tesla has to make some serious progress with, because parking has truly stumped FSD at times.

Solving that will be a major breakthrough for autonomy, but Tesla has struggled with it for some time.

All in all, FSD v14.3.3 is unbelievably accurate and handles many of the more stressful maneuvers with ease, one of them being avoiding merging traffic on highways, which was shown above.

Some things that would be great to see improvements on are parking, Speed Profiles, which are relatively tough to adjust (I stayed in Standard for the duration of this drive), and, of course, navigation.

A Tesla Model 3 plunged roughly 300 feet off a cliff on Mulholland Highway in Malibu on Friday morning, May 29, 2026, and both occupants survived. The crash was reported at approximately 7:30 a.m. near the 2500 block of Mulholland Highway, triggering a multi-agency rescue operation involving Malibu Search and Rescue, the Los Angeles County Fire Department, the California Highway Patrol, and McCormick Ambulance.

When first responders arrived, the male driver was outside the vehicle shouting for help while the female passenger remained pinned inside the Tesla. Rescue crews rappelled down the cliffside on ropes to reach the wreckage. A flight medic was lowered by helicopter to begin treating both victims, and the driver was hoisted up to the roadway before crews used the Jaws of Life to free the trapped passenger. Both were airlifted to a local trauma center with moderate injuries despite a remarkable result for a fall that steep.

The outcome is not surprising, considering Model 3 earned an overall 5-star rating from NHTSA in every category and sub-category, and recorded the lowest probability of injury of any car ever evaluated by the U.S. New Car Assessment Program. The absence of a traditional engine in the front of the vehicle creates a longer crumple zone that absorbs impact energy before it reaches occupants, and the battery pack running along the floor gives the car an unusually low center of gravity that reinforces structural rigidity.

This is not the first time a Tesla has kept passengers alive after going off a cliff. A Tesla Model Y carrying a family of four survived a plunge off a cliff at Devil’s Slide near San Francisco in January 2023, with two adults and two children walking away from a 250-foot fall. That incident drew widespread attention to how the structural integrity of Tesla’s electric platform performs in extreme crash scenarios that most vehicles would not survive.

Tesla Model Y driver who drove off cliff with family attempts to avoid criminal conviction

Tesla Full Self-Driving v14.3.2 began rolling out to some owners earlier this week, and there are some notable improvements that came with this update.

There were two new lines of improvements in the release notes: one addressing Actually Smart Summon (ASS), and another that now allows drivers to choose a reason for an intervention via a small menu during disengagement.

Overall operation saw a handful of slight improvements, especially with parking performance, which has been the most notable difference with the arrival of FSD v14.3. However, there are still some very notable shortcomings, most notably with region-specific signage and navigation.

Tesla Assisted Smart Summon (ASS) improvements

There are noticeable improvements to ASS operation, which has definitely been inconsistent in terms of performance. Tesla wrote in the release notes for v14.3.2:

“Unified the model between Actually Smart Summon, FSD, and Robotaxi for more capable and reliable behavior.”

As recently as this month, I used Summon with no success. It had pulled around the parking lot I was in incorrectly, leaving the range at which Summon can be operated and losing a signal while moving in the middle of the lot.

This caused me to sprint across the lot to retrieve the vehicle:

It was pouring when I left the gym so I tried to Summon my Model Y

It turned the opposite way and drove out of range, stopping here and forcing me to walk even further across the lot in the rain for it 🤣

Advertisement

One day pic.twitter.com/iD10c8sriB

— TESLARATI (@Teslarati) April 5, 2026

Unfortunately, Summon was not dependable or accurate enough to use regularly. It appears Tesla might have bridged the gap needed to make it an effective feature, as two tests in parking lots proved that Summon was more responsive and faster to navigate to the location chosen.

It also did so without hesitation, confidently, and at a comfortable speed. I was able to test it twice at different distances:

🚨 Tesla FSD v14.3.2 ASS testing part 1

This was a significant improvement than recent tries using ASS. The parking lot was pretty empty but getting it to come to my location in one singular motion and maneuver was encouraging. https://t.co/vF7TS48GGV pic.twitter.com/sYt8tyHgNn

— TESLARATI (@Teslarati) April 23, 2026

Tesla Full Self-Driving v14.3.2 ASS testing part 2 https://t.co/lxfWfnLUxf pic.twitter.com/2R0r3ohI3M

— TESLARATI (@Teslarati) April 23, 2026

I plan to test this more thoroughly and regularly through the next few weeks, and I avoided using it in a congested parking lot initially because I have not had overwhelming success with Summon in the past. I wanted to set a low baseline for it to see if it could simply pull up to the place I pinned in the Tesla app.

It was two for two, which is a big improvement because I don’t think I ever had successful Summon attempts back-to-back. It just seems more confident than ever before.

New Disengagement Categories

This is a really good idea from Tesla, but there are some issues with it. The categories you can select are Critical, Comfort, Preference, and Other.

I think the reasons why people choose to take over would be a better way to prompt drivers, like, “Traveling Too Fast,” “Incorrect Maneuver,” “Navigation Error,” would be more beneficial.

I say this because it seems that how we each categorize things might be different. For example, I shared a video of an intervention because the car had navigated to an exit to a parking lot and put its left blinker on, despite left turns not being allowed there.

I disengaged and chose Critical as the reason; it’s not a comfort issue, it’s not a preference, it’s quite literally an illegal turn, and it’s also dangerous because it cuts across several lanes of traffic and is 180 degrees.

I chose to label this Navigation error as “Critical” while testing FSD v14.3.2

Here’s why:
✅ This intervention wasn’t “preference,” as the maneuver FSD routed was illegal
✅ If a police officer saw this maneuver, it would result in a ticket https://t.co/znhHb4haAo pic.twitter.com/bZOiLwWmQa

— TESLARATI (@Teslarati) April 23, 2026

Some said I should not have labeled this as Critical, but that’s the description I best characterized the disengagement as.

Categorizing interventions is a good thing, but it’s kind of hard to determine how to label them correctly.

Inconsistency with Regional Traffic Patterns

Tesla Full Self-Driving is pretty inconsistent with how it handles regional or local traffic patterns and road rules. The most frequent example I like to use is that of the “Except Right Turn” stop sign, which has become a notorious sighting on our social media platforms.

In the initial rollout of v14.3, my Model Y successfully navigated through one of these stop signs with no issues. However, testing at two of these stop signs yesterday proved it is still not sure how to read signs and navigate through them properly.

🚨 Tesla FSD v14.3.2 attempts the “Except Right Turn” stop sign: https://t.co/W5MjAybaNK pic.twitter.com/P6oeUsk4PN

— TESLARATI (@Teslarati) April 23, 2026

Advertisement

Off camera, I approached another one of these signs and felt the car coming to a stop, so I nudged it forward with the accelerator pedal pressed.

This helped the car go through the sign without stopping, but I could feel the bucking of the vehicle as the car really wanted to stop.

Musk said on the earnings call earlier this week that unsupervised FSD would probably be available in some regions before others, including a state-to-state basis in the U.S.

“It’s difficult to release this like to everyone everywhere all at once because we do want to make sure that they’re not unique situations in a city that particularly complex intersection or — actually, they tend to be places where people get into accidents a lot because they’re just — perhaps there’s — and like I said, an unsafe intersection or bad road markings or a lot of weather challenges. So I think we would release unsupervised gradually to the customer fleet as we feel like a particular geography is confirmed to be safe.”

This could be one of those examples that Tesla just has to figure out.

Highway Operation

Full Self-Driving is already pretty good at routine roadway navigation, so I don’t have too much to report here.

However, I was happy with FSD’s decision-making at several points, including its choice not to pass a slightly slower car and remain in the right lane as we approached the off-ramp:

🚨 Tesla FSD v14.3.2 highway operation: generally happy with the performance here, especially behavior near the exit

Love that the car got over in the right lane after its final pass, and stayed there as the off ramp was approaching https://t.co/qVRVhg6XGR pic.twitter.com/1ELwHf2XKS

— TESLARATI (@Teslarati) April 23, 2026

Better Maneuvering at Stop Signs

Many FSD users report some strange operations at stop signs, especially four-way intersections where there is a stop sign and a line on the road, and they’re not even with one another.

I experienced this quite frequently and found that FSD would actually double stop: once at the stop sign and again at the line.

This created some interesting scenarios for me and I had many cars honk at me when the second stop would happen. Other vehicles that had waved me on to proceed through the intersection would become frustrated at the second stop.

FSD seems to have worked through this particular maneuver:

🚨 Tesla FSD v14.3.2 with a singular stop at the correct spot

No double stopping anymore in my experience https://t.co/Wd0TaNjc1R pic.twitter.com/CdQPvJHaAM

Advertisement

— TESLARATI (@Teslarati) April 23, 2026

FSD should know to go to the more appropriate location (whichever provides better visibility), and proceed when it is the car’s turn to move. The double stop really ruined the flow of traffic at times and generally caused some frustration from other drivers.